MétaCan
Menu
Back to cohort
Record W4317181824 · doi:10.1289/isee.2022.o-op-019

Characterization of urban built and natural environments with high-resolution satellite images and unsupervised deep learning

2022· article· en· W4317181824 on OpenAlexaff
Antje Barbara Metzler, Ricky Nathvani, Viktoriia Sharmanska, Wenjia Bai, Emily Muller, Simon Moulds, Charles Agyei‐Asabere, Dina Adjei-Boadi, Elvis Kyere-Gyeabour, Jacob Doku Tetteh, George Owusu, Samuel Agyei‐Mensah, Jill Baumgartner, Brian E. Robinson, Raphael E. Arku, Majid Ezzati

Bibliographic record

VenueISEE Conference Abstracts · 2022
Typearticle
Languageen
FieldEnvironmental Science
TopicLand Use and Ecosystem Services
Canadian institutionsMcGill University
Fundersnot available
KeywordsCluster analysisVegetation (pathology)Unsupervised learningScale (ratio)GeographyUrban planningDeep learningBuilt environmentSatellite imageryCartographyRemote sensingPopulationSatelliteComputer scienceEnvironmental resource managementEnvironmental scienceArtificial intelligenceEcologyEnvironmental health

Abstract

fetched live from OpenAlex

BACKGROUND AND AIM: Cities in the developing world are expanding rapidly and undergoing changes to their roads, housing and other buildings, vegetation, and land use characteristics. Timely data are needed to ensure that urban change enhance health, wellbeing and sustainability. METHODS: We characterise, as mutually exclusive clusters, the complex, multidimensional, built and natural environments in cities with high-resolution satellite images and unsupervised deep clustering. We apply our approach to Accra, Ghana, one of the fastest growing cities in the developing world, and contextualise the resultant clusters with demographic and environmental data that were not used for clustering. RESULTS: We show that image-based clusters captured distinct features of the urban built environment (building count, size, density, and orientation; length and arrangement of roads), vegetation, water, and population, either as a unique defining characteristic (e.g., bodies of water or dense vegetation) or in combination (e.g., buildings surrounded by vegetation or sparsely populated areas intermixed with roads). Clusters that were based on single defining characteristics were robust to the spatial scale of analysis and choice of cluster number, whereas those based on a combination of defining characteristics changed based on scale and number of clusters. CONCLUSION: The results demonstrate that satellite data and unsupervised deep learning provide a cost-effective interpretable and scalable approach for real-time tracking of sustainable urban development, especially where traditional environmental and demographic data are limited and not frequently updated. Our approach has multiple urban environmental applications, such as providing ground data for tracking and measuring urban health, air- and noise pollution, urban connectivity and road traffic, as well as city growth in cities across Africa and beyond. KEYWORDS: Big data, satellite imagery, deep learning, built environment; urban growth, unsupervised machine learning

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.019
Threshold uncertainty score0.038

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0020.001
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.007
GPT teacher head0.182
Teacher spread0.175 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueISEE Conference AbstractsSame topicLand Use and Ecosystem ServicesFrench-language works237,207